Purpose¶

The purpose of this notebook is to clean the immoscout_cleaned_lat_lon_fixed_v9.csv file, save it and generate an automated exploratory analysis report.

In [ ]:
# Import modules
import pandas as pd
from utils.helper_v1 import ImmoHelper
import sweetviz as sv
In [ ]:
helper = ImmoHelper()
df = helper.process_data(return_gde=True)
In [ ]:
# reorder columns alphabetically and show sweetviz report
df = df.reindex(sorted(df.columns), axis=1)
sweet_report = sv.analyze(df)
sweet_report.show_notebook()
                                             |          | [  0%]   00:00 -> (? left)
In [ ]:
df.to_csv('../../data/clean_gde.csv')
In [ ]:
df = helper.process_data(return_gde=False)
In [ ]:
df.to_csv('../../data/clean.csv')